Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟱𝟳 Computer Vision Learning RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds by University of Oxford Follow me for similar post :  🇮🇳 Ashish Patel 𝗜𝗡𝗧𝗘𝗥𝗘𝗦𝗧𝗜𝗡𝗚 𝗙𝗔𝗖𝗧𝗦 : 🔸 This is a paper in CVPR 2020 with over 177 citations. 🔸 It Outperforms PointNet, SPG, SPLATNet, PointNet++, TangentConv etc. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eum5ZJw code :https://lnkd.in/ez6QxxR ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. 🔸𝗥𝗔𝗡𝗗𝗟𝗔-𝗡𝗘𝗧, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. #computervision #artificialintelligence #data